AI RESEARCH
Making Written Theorems Explorable by Grounding Them in Formal Representations
arXiv CS.AI
•
ArXi:2604.02598v1 Announce Type: cross LLM-generated explanations can make technical content accessible, but there is a ceiling on what they can interactively. Because LLM outputs are static text, they cannot be executed or stepped through. We argue that grounding explanations in a formalized representation enables interactive affordances beyond what static text s.